Multi-domain Aspect Extraction Based on Deep and Lifelong Learning

Dionis López; Leticia Arco

doi:10.1007/978-3-030-33904-3_52

Multi-domain Aspect Extraction Based on Deep and Lifelong Learning

Dionis López, Leticia Arco

Informatics and Applied Informatics

Research output: Chapter in Book/Report/Conference proceeding › Chapter › Research › peer-review

Abstract

Opinions concerning features or aspects of people, entities, products or services are some of the most important textual information. Several methods try to solve the aspect extraction task needed in sentiment analysis by using Deep Learning techniques in specific domains. However, catastrophic forgetting appears when these methods are used to learn aspects of multi-domains. In this paper, we propose a new approach to achieve aspect extraction in multi-domains based on Deep and Lifelong Learning techniques. Our proposal reduces catastrophic forgetting and improves one of the principal state-of-the-art results.

Original language	English
Title of host publication	Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications
Editors	Ingela Nyström, Yanio Hernández Heredia, Vladimir Milián Núñez
Publisher	Springer Verlag
Pages	556-565
Number of pages	10
Volume	11896
ISBN (Electronic)	978-3-030-33904-3
ISBN (Print)	978-3-030-33903-6
DOIs	https://doi.org/10.1007/978-3-030-33904-3_52
Publication status	Published - 22 Oct 2019

Publication series

Name	Lecture Notes in Computer Science book series
Publisher	Springer, Cham
Volume	11896

Keywords

opinion mining
aspect extraction
deep learning
lifelong learning

Access to Document

10.1007/978-3-030-33904-3_52

1 Talk or presentation at a conference

Multi-domain Aspect Extraction Based on Deep and Lifelong Learning
Dionis López (Speaker) & Leticia Arco Garcia (Speaker)
28 Oct 2019 → 31 Oct 2019
Activity: Talk or presentation › Talk or presentation at a conference

Cite this

López, D., & Arco, L. (2019). Multi-domain Aspect Extraction Based on Deep and Lifelong Learning. In I. Nyström, Y. Hernández Heredia, & V. Milián Núñez (Eds.), Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications (Vol. 11896, pp. 556-565). (Lecture Notes in Computer Science book series; Vol. 11896). Springer Verlag. https://doi.org/10.1007/978-3-030-33904-3_52

@inbook{729bb1f49e6d4a14897d60ac0fb067bc,

title = "Multi-domain Aspect Extraction Based on Deep and Lifelong Learning",

abstract = "Opinions concerning features or aspects of people, entities, products or services are some of the most important textual information. Several methods try to solve the aspect extraction task needed in sentiment analysis by using Deep Learning techniques in specific domains. However, catastrophic forgetting appears when these methods are used to learn aspects of multi-domains. In this paper, we propose a new approach to achieve aspect extraction in multi-domains based on Deep and Lifelong Learning techniques. Our proposal reduces catastrophic forgetting and improves one of the principal state-of-the-art results.",

keywords = "opinion mining, aspect extraction, deep learning, lifelong learning",

author = "Dionis L{\'o}pez and Leticia Arco",

year = "2019",

month = oct,

day = "22",

doi = "10.1007/978-3-030-33904-3_52",

language = "English",

isbn = "978-3-030-33903-6",

volume = "11896",

series = "Lecture Notes in Computer Science book series",

publisher = "Springer Verlag",

pages = "556--565",

editor = "Ingela Nystr{\"o}m and {Hern{\'a}ndez Heredia}, Yanio and {Mili{\'a}n N{\'u}{\~n}ez}, Vladimir",

booktitle = "Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications",

address = "Germany",

}

López, D & Arco, L 2019, Multi-domain Aspect Extraction Based on Deep and Lifelong Learning. in I Nyström, Y Hernández Heredia & V Milián Núñez (eds), Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications. vol. 11896, Lecture Notes in Computer Science book series, vol. 11896, Springer Verlag, pp. 556-565. https://doi.org/10.1007/978-3-030-33904-3_52

Multi-domain Aspect Extraction Based on Deep and Lifelong Learning. / López, Dionis; Arco, Leticia.

Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications. ed. / Ingela Nyström; Yanio Hernández Heredia; Vladimir Milián Núñez. Vol. 11896 Springer Verlag, 2019. p. 556-565 (Lecture Notes in Computer Science book series; Vol. 11896).

Research output: Chapter in Book/Report/Conference proceeding › Chapter › Research › peer-review

TY - CHAP

T1 - Multi-domain Aspect Extraction Based on Deep and Lifelong Learning

AU - López, Dionis

AU - Arco, Leticia

PY - 2019/10/22

Y1 - 2019/10/22

N2 - Opinions concerning features or aspects of people, entities, products or services are some of the most important textual information. Several methods try to solve the aspect extraction task needed in sentiment analysis by using Deep Learning techniques in specific domains. However, catastrophic forgetting appears when these methods are used to learn aspects of multi-domains. In this paper, we propose a new approach to achieve aspect extraction in multi-domains based on Deep and Lifelong Learning techniques. Our proposal reduces catastrophic forgetting and improves one of the principal state-of-the-art results.

AB - Opinions concerning features or aspects of people, entities, products or services are some of the most important textual information. Several methods try to solve the aspect extraction task needed in sentiment analysis by using Deep Learning techniques in specific domains. However, catastrophic forgetting appears when these methods are used to learn aspects of multi-domains. In this paper, we propose a new approach to achieve aspect extraction in multi-domains based on Deep and Lifelong Learning techniques. Our proposal reduces catastrophic forgetting and improves one of the principal state-of-the-art results.

KW - opinion mining

KW - aspect extraction

KW - deep learning

KW - lifelong learning

U2 - 10.1007/978-3-030-33904-3_52

DO - 10.1007/978-3-030-33904-3_52

M3 - Chapter

SN - 978-3-030-33903-6

VL - 11896

T3 - Lecture Notes in Computer Science book series

SP - 556

EP - 565

BT - Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications

A2 - Nyström, Ingela

A2 - Hernández Heredia, Yanio

A2 - Milián Núñez, Vladimir

PB - Springer Verlag

ER -

López D, Arco L. Multi-domain Aspect Extraction Based on Deep and Lifelong Learning. In Nyström I, Hernández Heredia Y, Milián Núñez V, editors, Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications. Vol. 11896. Springer Verlag. 2019. p. 556-565. (Lecture Notes in Computer Science book series). https://doi.org/10.1007/978-3-030-33904-3_52

Multi-domain Aspect Extraction Based on Deep and Lifelong Learning

Abstract

Publication series

Keywords

Access to Document

Fingerprint

Activities

Multi-domain Aspect Extraction Based on Deep and Lifelong Learning

Cite this